from Utils.s_plus import dot_product
import scipy.sparse as sps
from Base.Evaluation.Evaluator import EvaluatorHoldout
from GraphBased.RP3betaRecommender import RP3betaRecommender
from ParameterTuning.SearchBayesianSkopt import SearchBayesianSkopt
from skopt.space import Real, Integer, Categorical
from ParameterTuning.SearchAbstractClass import SearchInputRecommenderArgs
data = DataManager()
ucm_age, ucm_region, ucm_all = data.get_ucm()
icm_price, icm_asset, icm_sub, icm_all = data.get_icm()
recommender_4 = UserKNNCFRecommender(data.get_urm())
recommender_4.fit(shrink=2, topK=600, normalize=True)
W_sparse_CF = recommender_4.W_sparse
cfw = User_CFW_D_Similarity_Linalg(URM_train=data.get_urm(),
UCM=ucm_all.copy(),
S_matrix_target=W_sparse_CF
)
cfw.fit(topK=1740, add_zeros_quota=0.3528735601555612, normalize_similarity=True)
weights = sps.diags(cfw.D_best)
ucm_weighted = ucm_all.dot(weights)
sps.save_npz("Data/ucm_weighted.npz", ucm_weighted.tocsr())
def read_data_split_and_search():
"""
This function provides a simple example on how to tune parameters of a given algorithm
The BayesianSearch object will save:
- A .txt file with all the cases explored and the recommendation quality
- A _best_model file which contains the trained model and can be loaded with recommender.load_model()
- A _best_parameter file which contains a dictionary with all the fit parameters, it can be passed to recommender.fit(**_best_parameter)
- A _best_result_validation file which contains a dictionary with the results of the best solution on the validation
- A _best_result_test file which contains a dictionary with the results, on the test set, of the best solution chosen using the validation set
"""
seed = 1205
parser = DataParser()
URM_all = parser.get_URM_all()
ICM_obj = parser.get_ICM_all()
# SPLIT TO GET TEST PARTITION
URM_train, URM_test = split_train_in_two_percentage_global_sample(
URM_all, train_percentage=0.90, seed=seed)
# SPLIT TO GET THE HYBRID VALID PARTITION
URM_train, URM_valid_hybrid = split_train_in_two_percentage_global_sample(
URM_train, train_percentage=0.85, seed=seed)
# SPLIT TO GET THE sub_rec VALID PARTITION
URM_train_bis, URM_valid_sub = split_train_in_two_percentage_global_sample(
URM_train, train_percentage=0.85, seed=seed)
collaborative_algorithm_list = [
#EASE_R_Recommender
#PipeHybrid001,
#Random,
#TopPop,
#P3alphaRecommender,
#RP3betaRecommender,
#ItemKNNCFRecommender,
#UserKNNCFRecommender,
#MatrixFactorization_BPR_Cython,
#MatrixFactorization_FunkSVD_Cython,
#PureSVDRecommender,
#NMFRecommender,
#PureSVDItemRecommender
#SLIM_BPR_Cython,
#SLIMElasticNetRecommender
#IALSRecommender
#MF_MSE_PyTorch
#MergedHybrid000
#LinearHybrid002ggg
HybridCombinationSearch
]
content_algorithm_list = [
#ItemKNNCBFRecommender
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_valid_sub = EvaluatorHoldout(URM_valid_sub, cutoff_list=[10])
evaluator_valid_hybrid = EvaluatorHoldout(URM_valid_hybrid,
cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
"""
# TODO: setta I GIUSTI EVALUATOR QUI!!!!
runParameterSearch_Content_partial = partial(runParameterSearch_Content,
URM_train=URM_train,
ICM_object=ICM_obj,
ICM_name='1BookFeatures',
n_cases = 50,
n_random_starts = 20,
evaluator_validation= evaluator_valid_sub,
evaluator_test = evaluator_valid_hybrid,
metric_to_optimize = "MAP",
output_folder_path=output_folder_path,
parallelizeKNN = False,
allow_weighting = True,
#similarity_type_list = ['cosine']
)
pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1)
pool.map(runParameterSearch_Content_partial, content_algorithm_list)
"""
print("Rp3beta training...")
rp3b = RP3betaRecommender(URM_train, verbose=False)
rp3b_params = {
'topK': 1000,
'alpha': 0.38192761611274967,
'beta': 0.0,
'normalize_similarity': False
}
rp3b.fit(**rp3b_params)
print("Done")
print("P3alpha training...")
p3a = P3alphaRecommender(URM_train, verbose=False)
p3a_params = {
'topK': 131,
'alpha': 0.33660811631883863,
'normalize_similarity': False
}
p3a.fit(**p3a_params)
print("Done")
print("ItemKnnCF training...")
icf = ItemKNNCFRecommender(URM_train, verbose=False)
icf_params = {
'topK': 100,
'shrink': 1000,
'similarity': 'asymmetric',
'normalize': True,
'asymmetric_alpha': 0.0
}
icf.fit(**icf_params)
print("Done")
print("UserKnnCF training...")
ucf = UserKNNCFRecommender(URM_train, verbose=False)
ucf_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
ucf.fit(**ucf_params)
print("Done")
print("ItemKnnCBF training...")
icb = ItemKNNCBFRecommender(URM_train, ICM_obj, verbose=False)
icb_params = {
'topK': 205,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
icb.fit(**icb_params)
print("Done")
print("SlimBPR training...")
sbpr = SLIM_BPR_Cython(URM_train, verbose=False)
sbpr_params = {
'topK': 979,
'epochs': 130,
'symmetric': False,
'sgd_mode': 'adam',
'lambda_i': 0.004947329669424629,
'lambda_j': 1.1534760845071758e-05,
'learning_rate': 0.0001
}
sbpr.fit(**sbpr_params)
print("Done")
print("SlimElasticNet training...")
sen = SLIMElasticNetRecommender(URM_train, verbose=False)
sen_params = {
'topK': 992,
'l1_ratio': 0.004065081925341167,
'alpha': 0.003725005053334143
}
sen.fit(**sen_params)
print("Done")
list_recommender = [rp3b, p3a, icf, ucf, icb, sen, sbpr]
list_already_seen = [rp3b, p3a, icf, ucf, icb]
for rec_perm in combinations(list_recommender, 3):
if rec_perm not in combinations(list_already_seen, 3):
recommender_names = '_'.join(
[r.RECOMMENDER_NAME for r in rec_perm])
output_folder_path = "result_experiments_v3/seed_" + str(
seed) + '/' + recommender_names + '/'
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
# TODO: setta I GIUSTI EVALUATOR QUI!!!!
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
ICM_train=ICM_obj,
metric_to_optimize="MAP",
n_cases=50,
n_random_starts=20,
evaluator_validation_earlystopping=evaluator_valid_hybrid,
evaluator_validation=evaluator_valid_hybrid,
evaluator_test=evaluator_test,
output_folder_path=output_folder_path,
allow_weighting=False,
#similarity_type_list = ["cosine", 'jaccard'],
parallelizeKNN=False,
list_rec=rec_perm)
pool = multiprocessing.Pool(processes=int(
multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial,
collaborative_algorithm_list)
def read_data_split_and_search():
"""
This function provides a simple example on how to tune parameters of a given algorithm
The BayesianSearch object will save:
- A .txt file with all the cases explored and the recommendation quality
- A _best_model file which contains the trained model and can be loaded with recommender.load_model()
- A _best_parameter file which contains a dictionary with all the fit parameters, it can be passed to recommender.fit(**_best_parameter)
- A _best_result_validation file which contains a dictionary with the results of the best solution on the validation
- A _best_result_test file which contains a dictionary with the results, on the test set, of the best solution chosen using the validation set
"""
seed = 1205
parser = DataParser()
URM_all = parser.get_URM_all()
ICM_obj = parser.get_ICM_all()
# SPLIT TO GET TEST PARTITION
URM_train, URM_test = split_train_in_two_percentage_global_sample(
URM_all, train_percentage=0.90, seed=seed)
# SPLIT TO GET THE HYBRID VALID PARTITION
URM_train, URM_valid_hybrid = split_train_in_two_percentage_global_sample(
URM_train, train_percentage=0.85, seed=seed)
URM_valid_hybrid = parser.filter_URM_test_by_range(URM_train,
URM_valid_hybrid,
(3, -1))
collaborative_algorithm_list = [
# EASE_R_Recommender
# PipeHybrid001,
# Random,
# TopPop,
# P3alphaRecommender,
# RP3betaRecommender,
# ItemKNNCFRecommender,
# UserKNNCFRecommender,
# MatrixFactorization_BPR_Cython,
# MatrixFactorization_FunkSVD_Cython,
# PureSVDRecommender,
# NMFRecommender,
# PureSVDItemRecommender
# SLIM_BPR_Cython,
# SLIMElasticNetRecommender
# IALSRecommender
# MF_MSE_PyTorch
# MergedHybrid000
# LinearHybrid002ggg
HybridCombinationSearch
]
content_algorithm_list = [
# ItemKNNCBFRecommender
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_valid_hybrid = EvaluatorHoldout(URM_valid_hybrid,
cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
"""
earlystopping_keywargs = {"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_valid_hybrid,
"lower_validations_allowed": 5,
"validation_metric": 'MAP',
}
print('IALS training...')
ials = IALSRecommender(URM_train, verbose=False)
ials_params = {'num_factors': 83, 'confidence_scaling': 'linear', 'alpha': 28.4278070726612,
'epsilon': 1.0234211788885077, 'reg': 0.0027328110246575004, 'epochs': 20}
ials.fit(**ials_params, **earlystopping_keywargs)
print("Done")
print("PureSVD training...")
psvd = PureSVDRecommender(URM_train, verbose=False)
psvd_params = {'num_factors': 711}
psvd.fit(**psvd_params)
print("Done")
"""
print("Rp3beta training...")
rp3b = RP3betaRecommender(URM_train, verbose=False)
rp3b_params = {
'topK': 753,
'alpha': 0.3873710051288722,
'beta': 0.0,
'normalize_similarity': False
}
rp3b.fit(**rp3b_params)
print("Done")
print("P3alpha training...")
p3a = P3alphaRecommender(URM_train, verbose=False)
p3a_params = {
'topK': 438,
'alpha': 0.41923120471415165,
'normalize_similarity': False
}
p3a.fit(**p3a_params)
print("Done")
print("ItemKnnCF training...")
icf = ItemKNNCFRecommender(URM_train, verbose=False)
icf_params = {
'topK': 565,
'shrink': 554,
'similarity': 'tversky',
'normalize': True,
'tversky_alpha': 1.9109121434662428,
'tversky_beta': 1.7823834698905734
}
icf.fit(**icf_params)
print("Done")
print("UserKnnCF training...")
ucf = UserKNNCFRecommender(URM_train, verbose=False)
ucf_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
ucf.fit(**ucf_params)
print("Done")
print("ItemKnnCBF training...")
icb = ItemKNNCBFRecommender(URM_train, ICM_obj, verbose=False)
icb_params = {
'topK': 205,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
icb.fit(**icb_params)
print("Done")
"""
print("SlimElasticNet training...")
sen = SLIMElasticNetRecommender(URM_train, verbose=False)
sen_params = {'topK': 954, 'l1_ratio': 3.87446082207643e-05, 'alpha': 0.07562657698792305}
sen.fit(**sen_params)
print("Done")
"""
list_recommender = [icb, icf, ucf, p3a, rp3b]
list_already_seen = []
for rec_perm in combinations(list_recommender, 3):
if rec_perm not in combinations(list_already_seen, 3):
recommender_names = '_'.join(
[r.RECOMMENDER_NAME for r in rec_perm])
output_folder_path = "result_experiments_v3/seed_" + str(
seed) + '_3--1' + '/' + recommender_names + '/'
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
# TODO: setta I GIUSTI EVALUATOR QUI!!!!
runParameterSearch_Collaborative_partial = partial(
runParameterSearch_Collaborative,
URM_train=URM_train,
ICM_train=ICM_obj,
metric_to_optimize="MAP",
n_cases=50,
n_random_starts=20,
evaluator_validation_earlystopping=evaluator_valid_hybrid,
evaluator_validation=evaluator_valid_hybrid,
evaluator_test=evaluator_test,
output_folder_path=output_folder_path,
allow_weighting=False,
# similarity_type_list = ["cosine", 'jaccard'],
parallelizeKNN=False,
list_rec=rec_perm)
pool = multiprocessing.Pool(processes=int(
multiprocessing.cpu_count()),
maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial,
collaborative_algorithm_list)
def runParameterSearch_Collaborative(recommender_class,
URM_train,
ICM_1,
ICM_2,
metric_to_optimize="PRECISION",
evaluator_validation=None,
evaluator_test=None,
evaluator_validation_earlystopping=None,
output_root_path="result_experiments/",
parallelizeKNN=True,
n_cases=100):
from ParameterTuning.AbstractClassSearch import DictionaryKeys
# If directory does not exist, create
if not os.path.exists(output_root_path):
os.makedirs(output_root_path)
try:
output_root_path_rec_name = output_root_path + recommender_class.RECOMMENDER_NAME
parameterSearch = BayesianSearch(
recommender_class,
evaluator_validation=evaluator_validation,
evaluator_test=evaluator_test)
if recommender_class in [TopPop, Random]:
recommender = recommender_class(URM_train)
recommender.fit()
output_file = open(
output_root_path_rec_name + "_BayesianSearch.txt", "a")
result_dict, result_baseline = evaluator_validation.evaluateRecommender(
recommender)
output_file.write(
"ParameterSearch: Best result evaluated on URM_validation. Results: {}"
.format(result_baseline))
pickle.dump(
result_dict.copy(),
open(output_root_path_rec_name + "_best_result_validation",
"wb"),
protocol=pickle.HIGHEST_PROTOCOL)
result_dict, result_baseline = evaluator_test.evaluateRecommender(
recommender)
output_file.write(
"ParameterSearch: Best result evaluated on URM_test. Results: {}"
.format(result_baseline))
pickle.dump(result_dict.copy(),
open(output_root_path_rec_name + "_best_result_test",
"wb"),
protocol=pickle.HIGHEST_PROTOCOL)
output_file.close()
return
##########################################################################################################
if recommender_class is UserKNNCFRecommender:
similarity_type_list = ['cosine']
run_KNNCFRecommender_on_similarity_type_partial = partial(
run_KNNCFRecommender_on_similarity_type,
parameterSearch=parameterSearch,
URM_train=URM_train,
n_cases=n_cases,
output_root_path=output_root_path_rec_name,
metric_to_optimize=metric_to_optimize)
if parallelizeKNN:
pool = PoolWithSubprocess(processes=int(2), maxtasksperchild=1)
resultList = pool.map(
run_KNNCFRecommender_on_similarity_type_partial,
similarity_type_list)
else:
for similarity_type in similarity_type_list:
run_KNNCFRecommender_on_similarity_type_partial(
similarity_type)
return
##########################################################################################################
if recommender_class is ItemKNNCFRecommender:
similarity_type_list = ['cosine']
run_KNNCFRecommender_on_similarity_type_partial = partial(
run_KNNCFRecommender_on_similarity_type,
parameterSearch=parameterSearch,
URM_train=URM_train,
n_cases=n_cases,
output_root_path=output_root_path_rec_name,
metric_to_optimize=metric_to_optimize)
if parallelizeKNN:
pool = PoolWithSubprocess(processes=int(2), maxtasksperchild=1)
resultList = pool.map(
run_KNNCFRecommender_on_similarity_type_partial,
similarity_type_list)
else:
for similarity_type in similarity_type_list:
run_KNNCFRecommender_on_similarity_type_partial(
similarity_type)
return
##########################################################################################################
# if recommender_class is MultiThreadSLIM_RMSE:
#
# hyperparamethers_range_dictionary = {}
# hyperparamethers_range_dictionary["topK"] = [50, 100]
# hyperparamethers_range_dictionary["l1_penalty"] = [1e-2, 1e-3, 1e-4]
# hyperparamethers_range_dictionary["l2_penalty"] = [1e-2, 1e-3, 1e-4]
#
#
# recommenderDictionary = {DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
# DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
# DictionaryKeys.FIT_POSITIONAL_ARGS: dict(),
# DictionaryKeys.FIT_KEYWORD_ARGS: dict(),
# DictionaryKeys.FIT_RANGE_KEYWORD_ARGS: hyperparamethers_range_dictionary}
#
#
##########################################################################################################
if recommender_class is P3alphaRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800
]
hyperparamethers_range_dictionary["alpha"] = range(0, 2)
hyperparamethers_range_dictionary["normalize_similarity"] = [
True, False
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is HybridRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["w_itemcf"] = [
x * 0.1 + 1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_usercf"] = [
x * 0.1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_cbart"] = [
x * 0.1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_cbalb"] = [
x * 0.1 for x in range(0, 10)
]
hyperparamethers_range_dictionary["w_slim"] = [
x * 0.1 for x in range(0, 10)
]
#hyperparamethers_range_dictionary["w_svd"] = [x * 0.05 for x in range(0, 20)]
#hyperparamethers_range_dictionary["w_rp3"] = [x * 0.05 for x in range(0, 20)]
item = ItemKNNCFRecommender(URM_train)
user = UserKNNCFRecommender(URM_train)
SLIM = MultiThreadSLIM_ElasticNet(URM_train=URM_train)
item.fit(topK=800, shrink=10, similarity='cosine', normalize=True)
user.fit(topK=70, shrink=22, similarity='cosine', normalize=True)
SLIM.fit(l1_penalty=1e-05,
l2_penalty=0,
positive_only=True,
topK=150,
alpha=0.00415637376180466)
CBArt = ItemKNNCBFRecommender(ICM=ICM_1, URM_train=URM_train)
CBArt.fit(topK=160,
shrink=5,
similarity='cosine',
normalize=True,
feature_weighting="none")
CBAlb = ItemKNNCBFRecommender(ICM=ICM_2, URM_train=URM_train)
CBAlb.fit(topK=160,
shrink=5,
similarity='cosine',
normalize=True,
feature_weighting="none")
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"ICM_Art": ICM_1,
"ICM_Alb": ICM_2,
"item": item,
"user": user,
"SLIM": SLIM,
"CBArt": CBArt,
"CBAlb": CBAlb,
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is RP3betaRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
5, 10, 20, 50, 100, 150, 200, 300, 400, 500, 600, 700, 800
]
hyperparamethers_range_dictionary["alpha"] = range(0, 2)
hyperparamethers_range_dictionary["beta"] = range(0, 2)
hyperparamethers_range_dictionary["normalize_similarity"] = [True]
hyperparamethers_range_dictionary["implicit"] = [True]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is MatrixFactorization_FunkSVD_Cython:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["sgd_mode"] = ["adagrad", "adam"]
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["num_factors"] = range(
100, 1000, 20)
hyperparamethers_range_dictionary["reg"] = [0.0, 1e-3, 1e-6, 1e-9]
hyperparamethers_range_dictionary["learning_rate"] = [
1e-2, 1e-3, 1e-4, 1e-5
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validatons_allowed": 20,
"validation_metric": metric_to_optimize
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is FunkSVD:
hyperparamethers_range_dictionary = {}
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["num_factors"] = range(
100, 1000, 20)
hyperparamethers_range_dictionary["reg"] = [
0.0, 1e-03, 1e-06, 1e-09
]
hyperparamethers_range_dictionary["learning_rate"] = [1e-02, 1e-03]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is MatrixFactorization_AsySVD_Cython:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["sgd_mode"] = ["adagrad", "adam"]
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["num_factors"] = range(
100, 500, 10)
hyperparamethers_range_dictionary["batch_size"] = [
100, 200, 300, 400
]
hyperparamethers_range_dictionary["positive_reg"] = [
0.0, 1e-3, 1e-6, 1e-9
]
hyperparamethers_range_dictionary["negative_reg"] = [
0.0, 1e-3, 1e-6, 1e-9
]
hyperparamethers_range_dictionary["learning_rate"] = [
1e-2, 1e-3, 1e-4, 1e-5
]
hyperparamethers_range_dictionary["user_reg"] = [
1e-3, 1e-4, 1e-5, 1e-6
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {
'positive_threshold': 1
},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validatons_allowed": 20,
"validation_metric": metric_to_optimize
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is PureSVDRecommender:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["num_factors"] = list(
range(0, 250, 5))
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
#########################################################################################################
if recommender_class is SLIM_BPR_Cython:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [800, 900, 1000, 1200]
# hyperparamethers_range_dictionary["epochs"] = [1, 5, 10, 20, 30, 50, 70, 90, 110]
hyperparamethers_range_dictionary["sgd_mode"] = ["adagrad"]
hyperparamethers_range_dictionary["lambda_i"] = [1e-6]
hyperparamethers_range_dictionary["lambda_j"] = [1e-9]
hyperparamethers_range_dictionary["learning_rate"] = [
0.01, 0.001, 1e-4, 1e-5, 0.1
]
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {
'train_with_sparse_weights': True,
'symmetric': True,
'positive_threshold': 1
},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS: {
"validation_every_n": 10,
"stop_on_validation": True,
"evaluator_object": evaluator_validation_earlystopping,
"lower_validatons_allowed": 3,
"validation_metric": metric_to_optimize
},
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
##########################################################################################################
if recommender_class is MultiThreadSLIM_ElasticNet:
hyperparamethers_range_dictionary = {}
hyperparamethers_range_dictionary["topK"] = [
3300, 4300, 5300, 6300, 7300
]
hyperparamethers_range_dictionary["l1_penalty"] = [
1e-5, 1e-6, 1e-4, 1e-3
]
hyperparamethers_range_dictionary["l2_penalty"] = [1e-4]
hyperparamethers_range_dictionary["alpha"] = range(0, 1)
recommenderDictionary = {
DictionaryKeys.CONSTRUCTOR_POSITIONAL_ARGS: [URM_train],
DictionaryKeys.CONSTRUCTOR_KEYWORD_ARGS: {},
DictionaryKeys.FIT_POSITIONAL_ARGS:
dict(),
DictionaryKeys.FIT_KEYWORD_ARGS:
dict(),
DictionaryKeys.FIT_RANGE_KEYWORD_ARGS:
hyperparamethers_range_dictionary
}
#########################################################################################################
## Final step, after the hyperparameter range has been defined for each type of algorithm
best_parameters = parameterSearch.search(
recommenderDictionary,
n_cases=n_cases,
output_root_path=output_root_path_rec_name,
metric=metric_to_optimize)
except Exception as e:
print("On recommender {} Exception {}".format(recommender_class,
str(e)))
traceback.print_exc()
error_file = open(output_root_path + "ErrorLog.txt", "a")
error_file.write("On recommender {} Exception {}\n".format(
recommender_class, str(e)))
error_file.close()
base_recommenders = []
tested_recommenders = []
datas = [None] * anti_overfitting
tested_users = []
rec_model = []
for j in range(anti_overfitting):
data_reader = DataReader()
datas[j] = DataObject(data_reader, 1, random_seed=(50 + j * 10))
# TODO: Edit here
# TODO: If you edit here, remember to edit at the end too
# Insert the mix of recommender systems
rec1 = UserKNNCFRecommender(datas[j].urm_train)
rec1.fit(shrink=1000,
topK=1000,
similarity="cosine",
feature_weighting="TF-IDF")
rec2 = RP3betaRecommender(datas[j].urm_train)
rec2.fit(topK=5000, alpha=0.35, beta=0.025, implicit=True)
rec3 = ItemKNNCFRecommender(datas[j].urm_train)
rec3.fit(topK=200,
shrink=1000,
similarity="jaccard",
feature_weighting="TF-IDF")
rec4 = UserKNNCBFRecommender(datas[j].ucm_all, datas[j].urm_train)
rec4.fit(topK=5000,
shrink=5,
feature_weighting="TF-IDF",
similarity="euclidean")
rec5 = ItemKNNCBFRecommender(datas[j].urm_train,
datas[j].icm_all_augmented)
def read_data_split_and_search():
"""
This function provides a simple example on how to tune parameters of a given algorithm
The BayesianSearch object will save:
- A .txt file with all the cases explored and the recommendation quality
- A _best_model file which contains the trained model and can be loaded with recommender.load_model()
- A _best_parameter file which contains a dictionary with all the fit parameters, it can be passed to recommender.fit(**_best_parameter)
- A _best_result_validation file which contains a dictionary with the results of the best solution on the validation
- A _best_result_test file which contains a dictionary with the results, on the test set, of the best solution chosen using the validation set
"""
seed = 1205
parser = DataParser()
URM_all = parser.get_URM_all()
ICM_obj = parser.get_ICM_all()
# SPLIT TO GET TEST PARTITION
URM_train, URM_test = split_train_in_two_percentage_global_sample(URM_all, train_percentage=0.90, seed=seed)
# SPLIT TO GET THE HYBRID VALID PARTITION
URM_train, URM_valid_hybrid = split_train_in_two_percentage_global_sample(URM_train, train_percentage=0.85,
seed=seed)
collaborative_algorithm_list = [
# EASE_R_Recommender
# PipeHybrid001,
# Random,
# TopPop,
# P3alphaRecommender,
# RP3betaRecommender,
# ItemKNNCFRecommender,
# UserKNNCFRecommender,
# MatrixFactorization_BPR_Cython,
# MatrixFactorization_FunkSVD_Cython,
# PureSVDRecommender,
# NMFRecommender,
# PureSVDItemRecommender
# SLIM_BPR_Cython,
# SLIMElasticNetRecommender
# IALSRecommender
# MF_MSE_PyTorch
# MergedHybrid000
# LinearHybrid002ggg
HybridCombinationSearch
]
content_algorithm_list = [
# ItemKNNCBFRecommender
]
from Base.Evaluation.Evaluator import EvaluatorHoldout
evaluator_valid_hybrid = EvaluatorHoldout(URM_valid_hybrid, cutoff_list=[10])
evaluator_test = EvaluatorHoldout(URM_test, cutoff_list=[10])
"""
earlystopping_keywargs = {"validation_every_n": 5,
"stop_on_validation": True,
"evaluator_object": evaluator_valid_hybrid,
"lower_validations_allowed": 5,
"validation_metric": 'MAP',
}
print('IALS training...')
ials = IALSRecommender(URM_train, verbose=False)
ials_params = {'num_factors': 83, 'confidence_scaling': 'linear', 'alpha': 28.4278070726612,
'epsilon': 1.0234211788885077, 'reg': 0.0027328110246575004, 'epochs': 20}
ials.fit(**ials_params, **earlystopping_keywargs)
print("Done")
print("PureSVD training...")
psvd = PureSVDRecommender(URM_train, verbose=False)
psvd_params = {'num_factors': 711}
psvd.fit(**psvd_params)
print("Done")
"""
rp3b = RP3betaRecommender(URM_train, verbose=False)
rp3b_params = {'topK': 1000, 'alpha': 0.38192761611274967, 'beta': 0.0, 'normalize_similarity': False}
try:
rp3b.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{rp3b.RECOMMENDER_NAME}_for_second_search')
print(f"{rp3b.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {rp3b.RECOMMENDER_NAME} ...")
rp3b.fit(**rp3b_params)
print(f"done.")
rp3b.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{rp3b.RECOMMENDER_NAME}_for_second_search')
p3a = P3alphaRecommender(URM_train, verbose=False)
p3a_params = {'topK': 131, 'alpha': 0.33660811631883863, 'normalize_similarity': False}
try:
p3a.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{p3a.RECOMMENDER_NAME}_for_second_search')
print(f"{p3a.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {p3a.RECOMMENDER_NAME} ...")
p3a.fit(**p3a_params)
print(f"done.")
p3a.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{p3a.RECOMMENDER_NAME}_for_second_search')
icf = ItemKNNCFRecommender(URM_train, verbose=False)
icf_params = {'topK': 55, 'shrink': 1000, 'similarity': 'asymmetric', 'normalize': True, 'asymmetric_alpha': 0.0}
try:
icf.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{icf.RECOMMENDER_NAME}_for_second_search')
print(f"{icf.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {icf.RECOMMENDER_NAME} ...")
icf.fit(**icf_params)
print(f"done.")
icf.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{icf.RECOMMENDER_NAME}_for_second_search')
ucf = UserKNNCFRecommender(URM_train, verbose=False)
ucf_params = {'topK': 190, 'shrink': 0, 'similarity': 'cosine', 'normalize': True}
try:
ucf.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{ucf.RECOMMENDER_NAME}_for_second_search')
print(f"{ucf.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {ucf.RECOMMENDER_NAME} ...")
ucf.fit(**ucf_params)
print(f"done.")
ucf.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{ucf.RECOMMENDER_NAME}_for_second_search')
icb = ItemKNNCBFRecommender(URM_train, ICM_obj, verbose=False)
icb_params = {'topK': 65, 'shrink': 0, 'similarity': 'dice', 'normalize': True}
try:
icb.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{icb.RECOMMENDER_NAME}_for_second_search')
print(f"{icb.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {icf.RECOMMENDER_NAME} ...")
icb.fit(**icb_params)
print(f"done.")
icb.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{icb.RECOMMENDER_NAME}_for_second_search')
sen = SLIMElasticNetRecommender(URM_train, verbose=False)
sen_params = {'topK': 992, 'l1_ratio': 0.004065081925341167, 'alpha': 0.003725005053334143}
try:
sen.load_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{sen.RECOMMENDER_NAME}_for_second_search')
print(f"{sen.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {sen.RECOMMENDER_NAME} ...")
sen.fit(**sen_params)
print(f"done.")
sen.save_model(f'stored_recommenders/seed_{str(seed)}_hybrid_search/',
f'{sen.RECOMMENDER_NAME}_for_second_search')
print("\nStart.")
list_recommender = [icb, icf, ucf, p3a, rp3b, sen]
list_already_seen = []
combinations_already_seen = []
"""
(icb, icf, p3a), (icb, icf, rp3b), (icb, icf, sen), (icb, p3a, rp3b), (icb, p3a, sen),
(icb, rp3b, sen), (icf, p3a, rp3b), (icf, p3a, sen)
"""
for rec_perm in combinations(list_recommender, 3):
if rec_perm not in combinations_already_seen:
recommender_names = '_'.join([r.RECOMMENDER_NAME for r in rec_perm])
output_folder_path = "result_experiments_v3/seed_" + str(
seed) + '/linear_combination/' + recommender_names + '/'
print(F"\nTESTING THE COMBO {recommender_names}")
# If directory does not exist, create
if not os.path.exists(output_folder_path):
os.makedirs(output_folder_path)
# TODO: setta I GIUSTI EVALUATOR QUI!!!!
runParameterSearch_Collaborative_partial = partial(runParameterSearch_Collaborative,
URM_train=URM_train,
ICM_train=ICM_obj,
metric_to_optimize="MAP",
n_cases=50,
n_random_starts=20,
evaluator_validation_earlystopping=evaluator_valid_hybrid,
evaluator_validation=evaluator_valid_hybrid,
#evaluator_test=evaluator_test,
output_folder_path=output_folder_path,
allow_weighting=False,
# similarity_type_list = ["cosine", 'jaccard'],
parallelizeKNN=False,
list_rec=rec_perm)
pool = multiprocessing.Pool(processes=int(multiprocessing.cpu_count()), maxtasksperchild=1)
pool.map(runParameterSearch_Collaborative_partial, collaborative_algorithm_list)
class HybridLinear10Recommneder(BaseItemSimilarityMatrixRecommender):
RECOMMENDER_NAME = "HybridLinear10Recommender"
def __init__(self, URM_train, seed: int):
super(HybridLinear10Recommneder, self).__init__(URM_train)
self.slimBPR = SLIM_BPR_Cython(URM_train)
self.userKnnCF = UserKNNCFRecommender(URM_train)
#self.itemcf = ItemKNNCFRecommender(urm)
def fit(self, alpha=1):
self.slimBPR.fit(epochs=135,
topK=933,
symmetric=False,
sgd_mode='adagrad',
lambda_i=1.054e-05,
lambda_j=1.044e-05,
learning_rate=0.00029)
self.userKnnCF.fit(topK=201,
shrink=998,
similarity='cosine',
normalize=True,
feature_weighting='TF-IDF')
self.alpha = alpha
self.beta = 1 - alpha
#self.gamma = alpha_gamma_ratio
def _compute_item_score(self, user_id_array, items_to_compute=None):
# ATTENTION!
# THIS METHOD WORKS ONLY IF user_id_array IS A SCALAR AND NOT AN ARRAY
# TODO
scores_slimBPR = self.slimBPR._compute_item_score(
user_id_array=user_id_array)
scores_userKnnCF = self.userKnnCF._compute_item_score(
user_id_array=user_id_array)
# normalization
#slim_max = scores_slim.max()
#rp3_max = scores_rp3.max()
#itemcf_max = scores_itemcf.max()
#if not slim_max == 0:
# scores_slim /= slim_max
#if not rp3_max == 0:
# scores_rp3 /= rp3_max
#if not itemcf_max == 0:
# scores_itemcf /= itemcf_max
scores_total = self.alpha * scores_slimBPR + self.beta * scores_userKnnCF #+ self.gamma * scores_itemcf
return scores_total
def save_model(self, folder_path, file_name=None):
if file_name is None:
file_name = self.RECOMMENDER_NAME
self._print("Saving model in file '{}'".format(folder_path +
file_name))
dataIO = DataIO(folder_path=folder_path)
dataIO.save_data(file_name=file_name, data_dict_to_save={})
self._print("Saving complete")
URM = data.get_URM()
ICM = data.get_ICM()
URM_train = data.get_URM_train()
URM_test = data.get_URM_test()
print("URM_train shape : {}".format(URM_train.shape))
print("URM_test shape : {}".format(URM_test.shape))
print("ICM shape : {}".format(ICM.shape))
evaluator_test = SequentialEvaluator(URM_test, cutoff_list=[10])
evaluator_test = EvaluatorWrapper(evaluator_test)
UserBased = UserKNNCFRecommender(URM_train)
UserBased.fit(topK=500, shrink=10)
ContentBased = ItemKNNCBFRecommender(ICM, URM_train)
ContentBased.fit(topK=5, shrink=1000)
ItemKNNCF = ItemKNNCFRecommender(URM_train)
ItemKNNCF.fit(topK=400, shrink=50)
hybridRecommender_scores = ItemKNNScoresHybridRecommender_multiple(
URM_train, ItemKNNCF, ContentBased, UserBased)
hybridRecommender_scores.fit(weight_1=HYBRID_ICF_CB_UCF_WEIGHTS[0],
weight_2=HYBRID_ICF_CB_UCF_WEIGHTS[1],
weight_3=HYBRID_ICF_CB_UCF_WEIGHTS[2])
dict, _ = evaluator_test.evaluateRecommender(hybridRecommender_scores)
def __init__(self, urm_train, eurm=False):
super(HybridNormRecommender, self).__init__(urm_train)
self.data_folder = Path(__file__).parent.parent.absolute()
self.eurm = eurm
self.num_users = urm_train.shape[0]
urm_train = check_matrix(urm_train.copy(), 'csr')
recommender_1 = HybridGen2Recommender(urm_train, eurm=self.eurm)
recommender_1.fit()
# recommender_2 = ItemKNNCFRecommender(urm_train)
# recommender_2.fit(shrink=30, topK=20)
recommender_2 = ItemKNNCFRecommender(urm_train)
recommender_2.fit(topK=5,
shrink=500,
feature_weighting='BM25',
similarity='tversky',
normalize=False,
tversky_alpha=0.0,
tversky_beta=1.0)
recommender_3 = UserKNNCFRecommender(urm_train)
recommender_3.fit(shrink=2, topK=600, normalize=True)
# recommender_3 = UserKNNCFRecommender(urm_train)
# recommender_3.fit(topK=697, shrink=1000, feature_weighting='TF-IDF', similarity='tversky', normalize=False,
# tversky_alpha=1.0, tversky_beta=1.0)
recommender_4 = RP3betaRecommender(urm_train)
recommender_4.fit(topK=16,
alpha=0.03374950051351756,
beta=0.24087176329409027,
normalize_similarity=True)
recommender_5 = SLIM_BPR_Cython(urm_train)
recommender_5.fit(lambda_i=0.0926694015,
lambda_j=0.001697250,
learning_rate=0.002391,
epochs=65,
topK=200)
recommender_6 = ALSRecommender(urm_train)
recommender_6.fit(alpha=5, iterations=40, reg=0.3)
self.recommender_1 = recommender_1
self.recommender_2 = recommender_2
self.recommender_3 = recommender_3
self.recommender_4 = recommender_4
self.recommender_5 = recommender_5
self.recommender_6 = recommender_6
if self.eurm:
if Path(self.data_folder / 'Data/uicm_sparse.npz').is_file():
print("Previous uicm_sparse found")
self.score_matrix_1 = sps.load_npz(self.data_folder /
'Data/uicm_sparse.npz')
else:
print("uicm_sparse not found, create new one...")
self.score_matrix_1 = self.recommender_1._compute_item_matrix_score(
np.arange(self.num_users))
sps.save_npz(self.data_folder / 'Data/uicm_sparse.npz',
self.score_matrix_1)
self.score_matrix_2 = self.recommender_2._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_3 = self.recommender_3._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_4 = self.recommender_4._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_5 = self.recommender_5._compute_item_matrix_score(
np.arange(self.num_users))
self.score_matrix_6 = self.recommender_6._compute_item_score(
np.arange(self.num_users))
self.score_matrix_2 = normalize(self.score_matrix_2,
norm='l2',
axis=1)
self.score_matrix_3 = normalize(self.score_matrix_3,
norm='l2',
axis=1)
self.score_matrix_4 = normalize(self.score_matrix_4,
norm='l2',
axis=1)
self.score_matrix_5 = normalize(self.score_matrix_5,
norm='l2',
axis=1)
self.score_matrix_6 = normalize(self.score_matrix_6,
norm='l2',
axis=1)
class LinearHybrid002(BaseItemSimilarityMatrixRecommender):
RECOMMENDER_NAME = "LinearHybrid002"
# set the seed equal to the one of the parameter search!!!!
def __init__(self,
URM_train,
ICM_train,
submission=False,
verbose=True,
seed=1205):
super(LinearHybrid002, self).__init__(URM_train, verbose=verbose)
self.URM_train = URM_train
self.ICM_train = ICM_train
# seed 1205: 'topK': 190, 'shrink': 0, 'similarity': 'cosine', 'normalize': True
self.__rec1 = UserKNNCFRecommender(URM_train, verbose=False)
self.__rec1_params = {
'topK': 190,
'shrink': 0,
'similarity': 'cosine',
'normalize': True
}
# seed 1205: 'topK': 100, 'shrink': 1000, 'similarity': 'asymmetric', 'normalize': True, 'asymmetric_alpha': 0.0
self.__rec2 = ItemKNNCFRecommender(URM_train, verbose=False)
self.__rec2_params = {
'topK': 100,
'shrink': 1000,
'similarity': 'asymmetric',
'normalize': True,
'asymmetric_alpha': 0.0
}
# seed 1205: 'topK': 205, 'shrink': 1000, 'similarity': 'cosine', 'normalize': True, 'feature_weighting': 'BM25'
self.__rec3 = ItemKNNCBFRecommender(URM_train,
ICM_train,
verbose=False)
self.__rec3_params = {
'topK': 205,
'shrink': 1000,
'similarity': 'cosine',
'normalize': True,
'feature_weighting': 'BM25'
}
self.__a = self.__b = self.__c = None
self.seed = seed
self.__submission = submission
def fit(self, alpha=0.5, l1_ratio=0.5):
self.__a = alpha * l1_ratio
self.__b = alpha - self.__a
self.__c = 1 - self.__a - self.__b
if not self.__submission:
try:
self.__rec1.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
'best_for_LinearHybrid002')
print(f"{self.__rec1.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {self.__rec1.RECOMMENDER_NAME} ...")
self.__rec1.fit(**self.__rec1_params)
print(f"done.")
self.__rec1.save_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec1.RECOMMENDER_NAME}/',
'best_for_LinearHybrid002')
try:
self.__rec2.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
'best_for_LinearHybrid002')
print(f"{self.__rec2.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {self.__rec2.RECOMMENDER_NAME} ...")
self.__rec2.fit(**self.__rec2_params)
print(f"done.")
self.__rec2.save_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec2.RECOMMENDER_NAME}/',
'best_for_LinearHybrid002')
try:
self.__rec3.load_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
'best_for_LinearHybrid002')
print(f"{self.__rec3.RECOMMENDER_NAME} loaded.")
except:
print(f"Fitting {self.__rec3.RECOMMENDER_NAME} ...")
self.__rec3.fit(**self.__rec3_params)
print(f"done.")
self.__rec3.save_model(
f'stored_recommenders/seed_{str(self.seed)}_{self.__rec3.RECOMMENDER_NAME}/',
'best_for_LinearHybrid002')
else:
self.__rec1.fit(**self.__rec1_params)
self.__rec2.fit(**self.__rec2_params)
self.__rec3.fit(**self.__rec3_params)
def _compute_item_score(self, user_id_array, items_to_compute=None):
item_weights_1 = self.__rec1._compute_item_score(user_id_array)
item_weights_2 = self.__rec2._compute_item_score(user_id_array)
item_weights_3 = self.__rec3._compute_item_score(user_id_array)
item_weights = item_weights_1 * self.__a + item_weights_2 * self.__b + item_weights_3 * self.__c
return item_weights
def save_model(self, folder_path, file_name=None):
if file_name is None:
file_name = self.RECOMMENDER_NAME
self._print("Saving model in file '{}'".format(folder_path +
file_name))
dataIO = DataIO(folder_path=folder_path)
dataIO.save_data(file_name=file_name, data_dict_to_save={})
self._print("Saving complete")
for recommender_class in recommender_list:
try:
print("Algorithm: {}".format(recommender_class))
recommender = recommender_class(URM_train)
item = ItemKNNCFRecommender(URM_train)
user = UserKNNCFRecommender(URM_train)
SLIM = MultiThreadSLIM_ElasticNet(URM_train=URM_train)
item.fit(topK=800, shrink=10, similarity='cosine', normalize=True)
user.fit(topK=70, shrink=22, similarity='cosine', normalize=True)
SLIM.fit(l1_penalty=1e-05,
l2_penalty=0,
positive_only=True,
topK=150,
alpha=0.00415637376180466)
recommender.fit(ICM_Art,
ICM_Alb,
item=item,
user=user,
SLIM=SLIM,
w_itemcf=1.1,
w_usercf=0.6,
w_cbart=0.3,
